Proceedings ArticleDOI
Automatic Generation and Evaluation of Usable and Secure Audio reCAPTCHA
Mohit Jain,Rohun Tripathi,Ishita Bhansali,Pratyush Kumar +3 more
- pp 355-366
Reads0
Chats0
TLDR
This work proposes reCAPGen, a system that uses ASR for generating secure CAPTCHAs and finds that the proposed Last Two Words scheme was the most usable with success rate of >78.2% and low response time of <14.5s.Abstract:
CAPTCHAs are challenge-response tests to differentiate humans from automated agents, with tasks that are easy for humans but difficult for computers. The most common CAPTCHAs require humans to decipher characters from an image and are unsuitable for visually impaired people. As an alternative, audio CAPTCHA was proposed, which require deciphering spoken digits/letters. However, current audio CAPTCHAs suffer from low usability and are insecure against Automatic Speech Recognition (ASR) attacks. In this work, we propose reCAPGen, a system that uses ASR for generating secure CAPTCHAs. We evaluated four audio CAPTCHA schemes with 60 sighted and 19 visually impaired participants. We found that our proposed Last Two Words scheme was the most usable with success rate of >78.2% and low response time of 82% accuracy.read more
Citations
More filters
Journal ArticleDOI
Gotta CAPTCHA ’Em All: A Survey of 20 Years of the Human-or-computer Dilemma
TL;DR: A recent study has found that malicious bots generated nearly a quarter of overall website traffic in 2019 as discussed by the authors, and these malicious bots perform activities such as price and content scraping, account creation, and account creation.
Proceedings ArticleDOI
Smartphone Usage by Expert Blind Users
TL;DR: In this paper, the authors present a detailed analysis that uncovered novel usage patterns, such as extensive usage of directional gestures, reliance on voice and external keyboard for text input, and repurposed explore by touch for single-tap.
Proceedings ArticleDOI
Accessibility-Related Publication Distribution in HCI Based on a Meta-Analysis
TL;DR: The authors presented a script-based meta-analysis on addressed populations in accessibility research published on top Human-Computer Interaction (HCI) venues (3617 full papers) and found that disability research could more reflect the prevalence of disabilities in the world.
References
More filters
Journal ArticleDOI
WordNet: a lexical database for English
TL;DR: WordNet1 provides a more effective combination of traditional lexicographic information and modern computing, and is an online lexical database designed for use under program control.
Book ChapterDOI
Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research
TL;DR: In this article, the results of a multi-year research program to identify the factors associated with variations in subjective workload within and between different types of tasks are reviewed, including task-, behavior-, and subject-related correlates of subjective workload experiences.
Book ChapterDOI
CAPTCHA: using hard AI problems for security
TL;DR: This work introduces captcha, an automated test that humans can pass, but current computer programs can't pass; any program that has high success over a captcha can be used to solve an unsolved Artificial Intelligence (AI) problem; and provides several novel constructions of captchas, which imply a win-win situation.
Journal ArticleDOI
reCAPTCHA: Human-Based Character Recognition via Web Security Measures
TL;DR: This research explored whether human effort can be channeled into a useful purpose: helping to digitize old printed material by asking users to decipher scanned words from books that computerized optical character recognition failed to recognize.
Journal ArticleDOI
Learning string-edit distance
TL;DR: The stochastic model allows us to learn a string-edit distance function from a corpus of examples and is applicable to any string classification problem that may be solved using a similarity function against a database of labeled prototypes.